// live pricing calculator

Find the cheapest model
for your exact usage

Drag the sliders to match your token usage and see real costs across every major LLM — updated live.

Input tokens 1,000
10K
Prompt + context sent to the model
Output tokens 500
2K
Completion generated by the model
Requests/month 1,000
10K
Total API calls per month
Quick pick:
Show: ·
Model Tier Input $/M Output $/M Per call Monthly total vs cheapest Context